Advanced Methods in Hyperspectral Imagery Analysis for Smart Sensing Applications

Hyperspectral imagery, an extension of traditional imaging, has proven to be a significant tool in various scientific fields due to its ability to detect and identify objects based on their unique spectral signatures. This project aims to focus on the application of hyperspectral imagery in remote sensing, food and drink, manufacturing and medical diagnosis. One of the primary challenges in hyperspectral imagery is the handling and processing of the vast amount of data these systems generate. Hyperspectral images contain information across a wide range of the electromagnetic spectrum, resulting in high-dimensional data that can be computationally intensive to process. Another limitation is the accuracy of classification and identification of materials or features, as the complexity of hyperspectral data can lead to ambiguities in interpretation.

To tackle with these limitations, this project will have the following objectives:

First, develop dimension reduction techniques to condense the high-dimensional hyperspectral data into more manageable formats without losing critical information. This will improve computational efficiency and facilitate more effective analysis.

Second, enhance band selection to identify the most relevant wavelengths for a given application. This allows customization of multispectral cameras to reduce costs, improving practicality of hyperspectral imaging.

Thirdly, the project will apply these advanced techniques to key computer vision tasks, specifically change detection and anomaly detection, to enhance decision-making in smart sensing applications. This includes diverse areas such as land mapping in remote sensing; retina and brain image analysis, aiding in early and accurate clinical diagnosis; non-destructive inspection for material characterization.

Diversity statement

Our research community thrives on the diversity of students and staff which helps to make the University of Dundee a UK university of choice for postgraduate research.  We welcome applications from all talented individuals and are committed to widening access to those who have the ability and potential to benefit from higher education.